← All roles

Research Engineer, Safety & Alignment

Cognition· Research & Development
Apply on company site
San FranciscoFull-timePosted 1w ago

About the role

We are an applied AI lab building end-to-end software agents. Devin is the first AI software engineer. The role focuses on safety and alignment of autonomous agents in production, with hands-on research engineering to run in-the-loop safety evaluations and improvements.

Responsibilities

  • Build agentic safety evals: Design and run evaluations for the failure modes that matter for autonomous agents: unsafe actions, prompt injection, data exfiltration, sandbox escape, reward hacking, and misuse. Make them fast enough to run on every model and product release.
  • Red-team Devin: Attack the agent and its harness systematically. Find the failures before customers do and turn them into fixes and regression tests.
  • Develop alignment methods: Work with post-training on reward modeling, preference data, constitutional approaches, and other techniques that make the model safer without making it worse at the job.
  • Shape the agent harness: Partner with the agent team on permissions, oversight, and escalation: when Devin should act, when it should ask, and how it should explain itself.
  • Publish and share: Contribute to Cognition's external safety work through papers, evals, and open methods where it makes sense.

Qualifications

  • Safety or alignment research experience: Hands-on work on evaluations, red-teaming, alignment, or interpretability at a frontier AI lab or in published research. You have built things that changed how a model was trained or deployed.
  • Agentic systems understanding: You know how agents fail in practice: tool misuse, specification gaming, long-horizon drift, adversarial inputs. You have measured it or have concrete ideas about how to.
  • Strong engineering fundamentals: Proficiency in Python and PyTorch (or JAX). You can build eval infrastructure, run experiments at scale, and read the training and inference code.
  • Empirical rigor: You design clean experiments, report results honestly, and know the difference between a real improvement and noise.
  • Comfort with adversarial thinking: You enjoy breaking systems and are good at it.
  • Relevant industry experience: Prior experience at a frontier AI lab, applied AI company, or developer tools company.
  • Advanced degree: PhD in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline; or equivalent industry research experience.

Skills

Required:PythonPyTorch (or JAX)Evaluations and red-teamingAgentic systems understandingEmpirical research methodsAdversarial thinking
Nice to have:Industry experienceAdvanced degree
Last updated Oct 21, 2026. Interested? Apply on the company site.
Cognition logo

About Cognition

cognition is an applied AI lab

An applied AI lab building the future of software engineering. We’re the makers of Devin, a collaborative AI teammate that helps ambitious engineering teams achieve more.

AIai-plg-top-20collaborative AIliquid-ai-recruiting-targetmachine learningsoftware engineering
Company profileWebsite

More open roles at Cognition